discovery-mission 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.gitignore +2 -0
- data/MIT_LICENCE +19 -0
- data/README.rdoc +37 -0
- data/Rakefile +17 -0
- data/discovery_mission.gemspec +13 -0
- data/discovery_mission.rb +56 -0
- data/spec.rb +65 -0
- metadata +73 -0
data/.gitignore
ADDED
data/MIT_LICENCE
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
Copyright (c) 2009 - 2010 Mickael Riga
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
+
of this software and associated documentation files (the "Software"), to deal
|
5
|
+
in the Software without restriction, including without limitation the rights
|
6
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
+
copies of the Software, and to permit persons to whom the Software is
|
8
|
+
furnished to do so, subject to the following conditions:
|
9
|
+
|
10
|
+
The above copyright notice and this permission notice shall be included in
|
11
|
+
all copies or substantial portions of the Software.
|
12
|
+
|
13
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
+
THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
= Discovery Mission
|
2
|
+
|
3
|
+
A SPACE ODYSSEY
|
4
|
+
|
5
|
+
This is just a simple, basic (dummy?) and lightweight crawler.
|
6
|
+
It is used to reference all URLs of your website in order to record them on a database, and use them for a sitemap manager.
|
7
|
+
|
8
|
+
Just install it:
|
9
|
+
|
10
|
+
# sudo gem install discovery-mission
|
11
|
+
|
12
|
+
And then you're ready to take off:
|
13
|
+
|
14
|
+
require 'discovery_mission'
|
15
|
+
|
16
|
+
# Use a block to do something with each path
|
17
|
+
# response is a 'net/http' response object, therefore responds to :body, :code ...
|
18
|
+
|
19
|
+
DiscoveryMission.for("http://www.my-domain.com") do |url, response|
|
20
|
+
puts "Dave Bowman landed on #{url}"
|
21
|
+
case response
|
22
|
+
when Net::HTTPSuccess
|
23
|
+
puts "Fuck you HAL 9000"
|
24
|
+
when Net::HTTPRedirection
|
25
|
+
puts "Shit! That's Jupiter!"
|
26
|
+
else
|
27
|
+
puts "Bad trip indeed"
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
# Or just without a block because an Array with all paths is returned
|
32
|
+
|
33
|
+
my_sitemap_entries = DiscoveryMission.for("http://www.my-domain.com")
|
34
|
+
|
35
|
+
-
|
36
|
+
|
37
|
+
Copyright (c) 2009 - 2010 Mickael Riga. See MIT_LICENCE file for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
spec = Gem::Specification.new do |s|
|
2
|
+
s.name = 'discovery_mission'
|
3
|
+
s.version = "0.0.1"
|
4
|
+
s.platform = Gem::Platform::RUBY
|
5
|
+
s.summary = "This is just a simple, basic (dummy?) and lightweight crawler."
|
6
|
+
s.files = ['discovery_mission.rb']
|
7
|
+
s.test_files = ['spec.rb']
|
8
|
+
s.require_path = '.'
|
9
|
+
s.autorequire = 'discovery_mission'
|
10
|
+
s.author = "Mickael Riga"
|
11
|
+
s.email = "mig@mypeplum.com"
|
12
|
+
s.homepage = "http://github.com/mig-hub/discovery_mission"
|
13
|
+
end
|
14
|
+
|
15
|
+
Rake::GemPackageTask.new(spec) do |pkg|
|
16
|
+
pkg.need_tar = true
|
17
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
Gem::Specification.new do |s|
|
2
|
+
s.name = 'discovery-mission'
|
3
|
+
s.version = "0.0.1"
|
4
|
+
s.platform = Gem::Platform::RUBY
|
5
|
+
s.summary = "A simple website crawler"
|
6
|
+
s.description = "Discovery Mission is an easy-to-use website crawler. Use it for generating sitemaps."
|
7
|
+
s.files = `git ls-files`.split("\n").sort
|
8
|
+
s.test_files = ['spec.rb']
|
9
|
+
s.require_path = '.'
|
10
|
+
s.author = "Mickael Riga"
|
11
|
+
s.email = "mig@mypeplum.com"
|
12
|
+
s.homepage = "http://github.com/mig-hub/discovery_mission"
|
13
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
require 'net/http'
|
2
|
+
require 'uri'
|
3
|
+
|
4
|
+
class DiscoveryMission
|
5
|
+
attr_accessor :roadmap
|
6
|
+
|
7
|
+
def self.for(domain, &block)
|
8
|
+
new(domain).launch(&block)
|
9
|
+
end
|
10
|
+
|
11
|
+
def initialize(domain)
|
12
|
+
@domain = URI(domain)
|
13
|
+
@domain.path = "/" if @domain.path == ""
|
14
|
+
reset
|
15
|
+
puts "\nDiscovery Mission Planned for #{@domain}\nEverything is under control Dave\n\n"
|
16
|
+
end
|
17
|
+
|
18
|
+
def launch
|
19
|
+
while destination = @roadmap.find {|k,v| v==false}
|
20
|
+
response = land_on(destination.first)
|
21
|
+
yield(destination.first, response) if block_given?
|
22
|
+
explore(destination.first, response)
|
23
|
+
@roadmap[destination.first] = true
|
24
|
+
end
|
25
|
+
uri_list = @roadmap.keys
|
26
|
+
reset
|
27
|
+
uri_list
|
28
|
+
end
|
29
|
+
|
30
|
+
def reset
|
31
|
+
@roadmap = {@domain.path => false}
|
32
|
+
end
|
33
|
+
|
34
|
+
def land_on(destination)
|
35
|
+
begin
|
36
|
+
response = Net::HTTP.get_response(@domain.host, destination)
|
37
|
+
rescue Exception
|
38
|
+
puts "Error: #{$!}"
|
39
|
+
end
|
40
|
+
return response
|
41
|
+
end
|
42
|
+
|
43
|
+
def explore(destination, response)
|
44
|
+
html = response.body
|
45
|
+
html.scan(/<a href\s*=\s*["']([^"']+)["']/i) do |w|
|
46
|
+
uri_found = URI("#{w}") rescue nil
|
47
|
+
unless (uri_found.nil? or (uri_found.absolute? and uri_found.host!=@domain.host) or (uri_found.path=='' or uri_found.path=='#' or uri_found.path[/^javascript/]))
|
48
|
+
destination += '/' unless destination[/\/$/]
|
49
|
+
uri_found.path = destination + uri_found.path unless uri_found.path[/^\//]
|
50
|
+
unless @roadmap.key?(uri_found.path)
|
51
|
+
@roadmap.store(uri_found.path, false)
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
56
|
+
end
|
data/spec.rb
ADDED
@@ -0,0 +1,65 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'bacon'
|
3
|
+
Bacon.summary_on_exit
|
4
|
+
|
5
|
+
MyResponse = Struct::new(:body)
|
6
|
+
|
7
|
+
def template_this(content)
|
8
|
+
"<html><head><title></title</head><body>#{content}</body></html>"
|
9
|
+
end
|
10
|
+
|
11
|
+
require File.expand_path('./discovery_mission', File.dirname(__FILE__))
|
12
|
+
class DiscoveryMission
|
13
|
+
attr_reader :roadmap
|
14
|
+
def land_on(destination)
|
15
|
+
destination=='/' ? MyResponse.new("<html><head><title></title</head><body><a href='/good/destination'>click</a></body></html>") : MyResponse.new('')
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
describe DiscoveryMission do
|
20
|
+
describe 'explore' do
|
21
|
+
before do
|
22
|
+
@dm = DiscoveryMission.new('http://www.domain.com')
|
23
|
+
end
|
24
|
+
it 'Should add correct destinations to roadmap' do
|
25
|
+
html = template_this("<a href='/good/destination'>click</a>")
|
26
|
+
@dm.explore("/", MyResponse.new(html))
|
27
|
+
@dm.roadmap.keys.should.include?('/good/destination')
|
28
|
+
end
|
29
|
+
it 'Should not raise when bad URI' do
|
30
|
+
html = template_this("<a href='http://'>click</a>")
|
31
|
+
@dm.explore("/", MyResponse.new(html))
|
32
|
+
@dm.roadmap.keys.should==["/"]
|
33
|
+
end
|
34
|
+
it 'Should skip pointless uri' do
|
35
|
+
html = template_this(<<-EOT)
|
36
|
+
<a href='http://www.another_domain.com'>click</a>
|
37
|
+
<a href='http://www.another_domain.com/with/path'>click</a>
|
38
|
+
<a href='#'>click</a>
|
39
|
+
<a href='javascript:void(0);'>click</a>
|
40
|
+
EOT
|
41
|
+
@dm.explore("/", MyResponse.new(html))
|
42
|
+
@dm.roadmap.keys.should==["/"]
|
43
|
+
end
|
44
|
+
it 'Sould add current path if uri is relative to it' do
|
45
|
+
html = template_this("<a href='chapter_one'>click</a>")
|
46
|
+
@dm.explore("/novel", MyResponse.new(html))
|
47
|
+
@dm.roadmap.keys.should.include?("/novel/chapter_one")
|
48
|
+
end
|
49
|
+
it 'Should not duplicate entries' do
|
50
|
+
html = template_this(<<-EOT)
|
51
|
+
<a href='/'>click</a>
|
52
|
+
<a href='http://www.domain.com'>click</a>
|
53
|
+
EOT
|
54
|
+
@dm.explore("/", MyResponse.new(html))
|
55
|
+
@dm.roadmap.keys.should==["/"]
|
56
|
+
end
|
57
|
+
end
|
58
|
+
describe 'launch' do
|
59
|
+
it 'Should be reseted for next launch' do
|
60
|
+
dm = DiscoveryMission.new('http://www.domain.com')
|
61
|
+
dm.launch.size.should==2
|
62
|
+
dm.roadmap.size.should==1
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
metadata
ADDED
@@ -0,0 +1,73 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: discovery-mission
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 29
|
5
|
+
prerelease: false
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
- 1
|
10
|
+
version: 0.0.1
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Mickael Riga
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2010-06-02 00:00:00 +01:00
|
19
|
+
default_executable:
|
20
|
+
dependencies: []
|
21
|
+
|
22
|
+
description: Discovery Mission is an easy-to-use website crawler. Use it for generating sitemaps.
|
23
|
+
email: mig@mypeplum.com
|
24
|
+
executables: []
|
25
|
+
|
26
|
+
extensions: []
|
27
|
+
|
28
|
+
extra_rdoc_files: []
|
29
|
+
|
30
|
+
files:
|
31
|
+
- .gitignore
|
32
|
+
- MIT_LICENCE
|
33
|
+
- README.rdoc
|
34
|
+
- Rakefile
|
35
|
+
- discovery_mission.gemspec
|
36
|
+
- discovery_mission.rb
|
37
|
+
- spec.rb
|
38
|
+
has_rdoc: true
|
39
|
+
homepage: http://github.com/mig-hub/discovery_mission
|
40
|
+
licenses: []
|
41
|
+
|
42
|
+
post_install_message:
|
43
|
+
rdoc_options: []
|
44
|
+
|
45
|
+
require_paths:
|
46
|
+
- .
|
47
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
48
|
+
none: false
|
49
|
+
requirements:
|
50
|
+
- - ">="
|
51
|
+
- !ruby/object:Gem::Version
|
52
|
+
hash: 3
|
53
|
+
segments:
|
54
|
+
- 0
|
55
|
+
version: "0"
|
56
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
hash: 3
|
62
|
+
segments:
|
63
|
+
- 0
|
64
|
+
version: "0"
|
65
|
+
requirements: []
|
66
|
+
|
67
|
+
rubyforge_project:
|
68
|
+
rubygems_version: 1.3.7
|
69
|
+
signing_key:
|
70
|
+
specification_version: 3
|
71
|
+
summary: A simple website crawler
|
72
|
+
test_files:
|
73
|
+
- spec.rb
|